pr-story

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes git diff and git status to identify code changes on the branch. It also uses the GitHub CLI (gh) to retrieve and update pull request metadata.
  • [DATA_EXFILTRATION]: The skill reads code changes and writes them to a PR description. This data flow is limited to the repository's own infrastructure and is consistent with the skill's primary function.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from code diffs (Category 8: Indirect Prompt Injection). However, the risk is mitigated by the 'Gate' in Phase 5, which requires explicit user approval before publishing the generated content.
  • [SAFE]: The skill uses established developer tools and follows a structured multi-phase process with human oversight, with no evidence of obfuscation or malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:33 PM
Security Audit — agent-trust-hub — pr-story